{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/morphnet-fast-simple-resource-constrained","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","arxiv_id":"1711.06798","date":"2017-11-18","proceeding":"CVPR 2018 6","authors":["Ariel Gordon","Elad Eban","Ofir Nachum","Bo Chen","Hao Wu","Tien-Ju Yang","Edward Choi"],"abstract":"We present MorphNet, an approach to automate the design of neural network\nstructures. MorphNet iteratively shrinks and expands a network, shrinking via a\nresource-weighted sparsifying regularizer on activations and expanding via a\nuniform multiplicative factor on all layers. In contrast to previous\napproaches, our method is scalable to large networks, adaptable to specific\nresource constraints (e.g. the number of floating-point operations per\ninference), and capable of increasing the network's performance. When applied\nto standard network architectures on a wide variety of datasets, our approach\ndiscovers novel structures in each domain, obtaining higher performance while\nrespecting the resource constraint.","url_abs":"http://arxiv.org/abs/1711.06798v3","url_pdf":"http://arxiv.org/pdf/1711.06798v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"morphnet-fast-simple-resource-constrained","repo_url":"https://github.com/NatGr/Master_Thesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"morphnet-fast-simple-resource-constrained","repo_url":"https://github.com/google-research/morph-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"morphnet-fast-simple-resource-constrained","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1711.06798","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}